© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8118
    Prev
    Next
    INDEX
    Explanations

    into

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uce
    -0.28
    åĩıå°ijäºĨ
    -0.27
    æĸ°é²ľ
    -0.27
    inka
    -0.26
     progressives
    -0.26
    çĭ¬çī¹
    -0.26
    ä¼ĺèī¯
    -0.26
    éĻįä½İ
    -0.26
    åĩıå°ij
    -0.25
    gel
    -0.25
    POSITIVE LOGITS
     uncertainty
    0.29
    æĭīçĿĢ
    0.28
     darkness
    0.27
     confusion
    0.27
    archy
    0.27
    annel
    0.26
     conflict
    0.26
    丼æŀĹ
    0.26
     hardship
    0.26
    ","+
    0.25
    Activations Density 0.002%

    No Known Activations